Sce2DriveX: A Generalized MLLM Framework for Scene-to-Drive Learning

TL;DR

Sce2DriveX is a multimodal large language model framework that enhances autonomous driving by integrating scene understanding, reasoning, and control, achieving state-of-the-art results and robust generalization across diverse driving scenarios.

Contribution

It introduces Sce2DriveX, a novel multimodal LLM framework with a chain-of-thought reasoning process for end-to-end autonomous driving, incorporating a new VQA dataset for 3D spatial understanding.

Findings

Achieves state-of-the-art performance in scene understanding and driving tasks.

Demonstrates robust generalization across different driving scenes.

Develops the first extensive VQA dataset for 3D spatial reasoning in driving.

Abstract

End-to-end autonomous driving, which directly maps raw sensor inputs to low-level vehicle controls, is an important part of Embodied AI. Despite successes in applying Multimodal Large Language Models (MLLMs) for high-level traffic scene semantic understanding, it remains challenging to effectively translate these conceptual semantics understandings into low-level motion control commands and achieve generalization and consensus in cross-scene driving. We introduce Sce2DriveX, a human-like driving chain-of-thought (CoT) reasoning MLLM framework. Sce2DriveX utilizes multimodal joint learning from local scene videos and global BEV maps to deeply understand long-range spatiotemporal relationships and road topology, enhancing its comprehensive perception and reasoning capabilities in 3D dynamic/static scenes and achieving driving generalization across scenes. Building on this, it reconstructs the implicit cognitive chain inherent in human driving, covering scene understanding, meta-action reasoning, behavior interpretation analysis, motion planning and control, thereby further bridging the gap between autonomous driving and human thought processes. To elevate model performance, we have developed the first extensive Visual Question Answering (VQA) driving instruction dataset tailored for 3D spatial understanding and long-axis task reasoning. Extensive experiments demonstrate that Sce2DriveX achieves state-of-the-art performance from scene understanding to end-to-end driving, as well as robust generalization on the CARLA Bench2Drive benchmark.